RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization

TL;DR

This paper introduces a large-scale dataset and a novel joint embedding method for cross-modal visual localization, matching ground RGB images to aerial LIDAR data, significantly advancing scalability and performance.

Contribution

It presents the first large-scale dataset and a new embedding approach for effective cross-modal localization between RGB and LIDAR images.

Findings

Achieved median rank of 5 in large-scale cross-modal matching

Created a dataset with over 550K image pairs covering 143 km^2

Demonstrated improved performance over prior methods

Abstract

We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (rendered as depth images). Prior works were demonstrated on small datasets and did not lend themselves to scaling up for large-scale applications. To enable large-scale evaluation, we introduce a new dataset containing over 550K pairs (covering 143 km^2 area) of RGB and aerial LIDAR depth images. We propose a novel joint embedding based method that effectively combines the appearance and semantic cues from both modalities to handle drastic cross-modal variations. Experiments on the proposed dataset show that our model achieves a strong result of a median rank of 5 in matching across a large test set of 50K location pairs collected from a 14km^2 area. This represents a significant advancement over prior works in performance and scale. We conclude with qualitative results to highlight the challenging nature of this task and the benefits of the proposed model. Our work provides a foundation for further research in cross-modal visual localization.